{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KKAXPDOX4BGQUTRPVH7LNCULK2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6eef96b530739d052ccce871588431e88a61208264e5291ce942730ed51c5058","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:14:12Z","title_canon_sha256":"9b941942d4f1123c114fd80a14e73b4082c925eb9425c918c5c7ed430b9249d6"},"schema_version":"1.0","source":{"id":"2410.20771","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20771","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20771v3","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20771","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_12","alias_value":"KKAXPDOX4BGQ","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_16","alias_value":"KKAXPDOX4BGQUTRP","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_8","alias_value":"KKAXPDOX","created_at":"2026-07-05T10:43:02Z"}],"graph_snapshots":[{"event_id":"sha256:48bd778fcc237c0f9b11ae87d1271b71522ea7cbcc00a506e0ec633e17683ca4","target":"graph","created_at":"2026-07-05T10:43:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.20771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level models like ByT5 attempt to address these concerns, they have not gained widespread adoption -- processing raw byte streams without tokenization results in significantly longer sequence lengths, making training and inference inefficient. This work introduces MrT5 (MergeT5), a more efficient variant of ByT5 that integrates a token deletion mechanism in its e","authors_text":"Christopher D. Manning, Christopher Potts, Julie Kallini, R\\'obert Csord\\'as, Shikhar Murty","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:14:12Z","title":"MrT5: Dynamic Token Merging for Efficient Byte-level Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20771","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dadfec82f451116537054563af537c6c43b52bba1d28ee55bc542f9fcbda1344","target":"record","created_at":"2026-07-05T10:43:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6eef96b530739d052ccce871588431e88a61208264e5291ce942730ed51c5058","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:14:12Z","title_canon_sha256":"9b941942d4f1123c114fd80a14e73b4082c925eb9425c918c5c7ed430b9249d6"},"schema_version":"1.0","source":{"id":"2410.20771","kind":"arxiv","version":3}},"canonical_sha256":"5281778dd7e04d0a4e2fa9feb68a8b56b21dc31dc9536790b8a24c2819a50086","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5281778dd7e04d0a4e2fa9feb68a8b56b21dc31dc9536790b8a24c2819a50086","first_computed_at":"2026-07-05T10:43:02.814804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:02.814804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AVpYSTR6xMkmYwXT7MPVD1mkAOt+9OGFrcZ408WBNa3X31KQIDc4S7cTy6zVC3jndp14oTl/qmHTrKoH7vJaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:02.815305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20771","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dadfec82f451116537054563af537c6c43b52bba1d28ee55bc542f9fcbda1344","sha256:48bd778fcc237c0f9b11ae87d1271b71522ea7cbcc00a506e0ec633e17683ca4"],"state_sha256":"7bcb4082d5f867a556808410301bf68220c8db16257157a7c288f391cf47f6c8"}